On its own, a model can only produce text. It cannot check today’s weather. It cannot look at your calendar. It cannot send an email. It can only write about doing so.
How Tool Use Works
The trick is surprisingly simple. You give the model a list of tools and describe what each one does. When it needs one, it writes a request in a fixed format. The software around the model reads that request, runs the tool, and hands back the result.
This is called tool use, or function calling. The model decides what to do. The software does it.
An Example
You ask, am I free on Friday afternoon? The model requests the calendar tool for Friday. The software returns two meetings, and the model answers.
From Writer to Worker
Now let the model use tools again and again: look something up, act on it, check the result, decide the next step. That loop is what people mean by an agent. This is where AI stops being a writer and becomes a worker.
Where the Risk Changes
A wrong sentence can be ignored. A wrong action, a payment, a deletion, an email, has consequences.
AI Agents builds on Tool Use. An agent is a model working in a loop, using tools, until the task is done.
MCP builds on Tool Use. MCP is a standard way to connect a model to tools and data, so each system builds one connector instead of many.
Prompt Injection constrains Tool Use. A wrong sentence can be ignored but a wrong action cannot; injected text can steer a tool-using assistant to forward invoices.
Tool Use builds on Structured Output(lesson unlocks soon). When the modelneeds a tool it writes a request in a fixed format, the structured output a program can read.
Generative UI(lesson unlocks soon) contrasts with Tool Use. Tool use lets a model act through tools; generative UI has the model build a small tool for the person to use.
The Business Engineer framework maps where each part of the AI stack sits and who holds the leverage. These pills are short lessons from the same library.
Gennaro Cuofano is a CRO and tech executive who has worked in AI since late 2015, starting with bringing NLP, natural-language generation, voice and chatbot products to the marketing industry. His background is in law and finance: he holds a Master's degree in Law and an International MBA with an emphasis on corporate finance (LUISS Business School and the University of San Diego, 2012), and worked as a financial analyst at a real-estate investment firm in San Diego and as an assistant controller. His work focuses on business model strategy, business engineering and, more broadly, structural analysis: how companies make money, read from their own filings. He created FourWeekMBA and leads research there and at The Business Engineer, his newsletter on AI and business strategy, with over 95,000 subscribers and more than 1,000 published analyses. His writing has also appeared on Entrepreneur (for example, How to Digitize a Family Business in Europe) and HackerNoon. Find him on LinkedIn and Substack. See how we source.
Scroll to Top
Discover more from FourWeekMBA
Subscribe now to keep reading and get access to the full archive.
